Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Depth adaptive video-splicing method, device and system thereof

A video stitching and depth compensation technology, applied in the field of computer vision, can solve the problems of not being able to achieve real-time or near-real-time work, time-consuming, etc., and achieve the effects of reducing ghost images, accelerating image mixing processing, and fast work

Inactive Publication Date: 2009-12-02
NEC (CHINA) CO LTD
View PDF1 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, simply adopting image stitching techniques in video stitching algorithms is not an effective strategy
Because the image alignment process is extremely time-consuming, this video stitching algorithm cannot work in real-time or near real-time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Depth adaptive video-splicing method, device and system thereof
  • Depth adaptive video-splicing method, device and system thereof
  • Depth adaptive video-splicing method, device and system thereof

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0143] Reference will be made below figure 1 and 5 The first embodiment of the present invention will be described in further detail.

[0144] figure 1 A block diagram of a video splicing system according to a first embodiment of the present invention is shown. like figure 1 As shown, the video splicing system includes a camera array 100 , a calibration device 200 , a splicing device 300 , and a pixel interpolator and mixer 400 .

[0145] The camera array 100 has at least two cameras and provides source video from the cameras to the calibration device 200 , the stitching device 300 , and the pixel interpolator and mixer 400 . In use, the user can select any camera in the camera array 100, and can also designate any one of the selected cameras as the camera of interest (ie, the image obtained by the camera is in the center of the field of view). At least two cameras in camera array 100 have overlapping fields of view.

[0146] The calibration device 200 is used to perform...

no. 2 example

[0154] Reference will be made below Image 6 and 7 The second embodiment of the present invention will be described in further detail.

[0155] Image 6 A block diagram of a video splicing system according to a second embodiment of the present invention is shown. and figure 1 Compared to the first embodiment shown, the index generator 260 in the calibration device 200 and the index updater 340 in the stitching device 300 are replaced by a single unit called a correspondence calculator 340'; The outputs of pole calibrator 210 and camera position calibrator 230 are directly connected to compensation calculator 330 . Other components of the second embodiment are similar to those of the first embodiment, and thus their detailed descriptions are omitted for clarity and simplicity.

[0156] Since the multiplier 270 is omitted, the calibration device 200 no longer outputs the desired epipolar transformation product. Therefore, the compensation calculator 330 needs to calculate ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a depth adaptive video-splicing method, a device and a system thereof. The depth adaptive video-splicing system comprises a camera array, a calibration device, a video-splicing device, a pixel interpolation device and a mixer, wherein a plurality of source videos are generated by the camera array; the calibration device executes antipodal calibration and camera position calibration, confirms a splicing area in each special adjacent image pair in a plurality of source videos and generates a pixel index table; the video-splicing device calculates an average pixel deviation value corresponding to the depth, forms a compensation item of the pixel index table based on the average pixel deviation value and compensates the pixel index table by the compensation item; and the pixel interpolation device and the mixer use the upgraded pixel index table and generate a panoramic video according to a plurality of source videos.

Description

technical field [0001] The present invention relates to the field of computer vision, and more particularly, to a method, device and system for depth adaptive video stitching. Background technique [0002] The technique of aligning and stitching images into a seamless photo mosaic is the earliest and most widely used technique in computer vision. This technique produces high-resolution photos that have been used to produce digital maps and satellite photos. Image stitching techniques are also currently implemented and embedded in digital cameras to obtain ultra-wide-angle photos. [0003] Video stitching technology is a special image stitching technology that provides wide-angle, high-resolution frame stitching from different video sources. With the rapid development of the display industry, extremely high-resolution displays are entering people's daily life. There is a need for high-resolution and wide-angle video in consumer electronics. Video stitching technology can ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/00H04N5/262
Inventor 曾炜张洪明
Owner NEC (CHINA) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products